5 papers · 1 filter
From Attribution to Action: A Human-Centered Application of Activation Steering
Tobias Labarta, Maximilian Dreyer, Katharina Weitz +2
Explainable AI (XAI) methods reveal which features influence model predictions, yet provide limited means for practitioners to act on these explanations. Activation steering of com…
X-SYS: A Reference Architecture for Interactive Explanation Systems
Tobias Labarta, Nhi Hoang, Maximilian Dreyer +5
The explainable AI (XAI) research community has proposed numerous technical methods, yet deploying explainability as systems remains challenging: Interactive explanation systems re…
Structural Compactness as a Complementary Criterion for Explanation Quality
Mohammad Mahdi Mesgari, Jackie Ma, Wojciech Samek +2
In the evaluation of attribution quality, the quantitative assessment of explanation legibility is particularly difficult, as it is influenced by varying shapes and internal organi…
Ensuring Medical AI Safety: Interpretability-Driven Detection and Mitigation of Spurious Model Behavior and Associated Data
Frederik Pahde, Thomas Wiegand, Sebastian Lapuschkin +1
Deep neural networks are increasingly employed in high-stakes medical applications, despite their tendency for shortcut learning in the presence of spurious correlations, which can…
Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers
Sayed Mohammad Vakilzadeh Hatefi, Maximilian Dreyer, Reduan Achtibat +3
To solve ever more complex problems, Deep Neural Networks are scaled to billions of parameters, leading to huge computational costs. An effective approach to reduce computational r…